Learning multi-level weight-centric features for few-shot learning

Highlights：

• We propose a weight-centric learning strategy that helps reduce the interclass variance of novel-class data.

• We propose a multi-level feature learning framework, which demonstrates its strong prototype-ability and transferability even in a cross-task environment for few-shot learning.

• We extensively evaluate our approach on two low-shot classification benchmarks in both standard and generalized FSL learning settings. Our results show that the mid-level features exhibit strong transferability even in a cross-task environment while the relation-level features help preserve base-class accuracy in the generalized FSL setting.